Description
TensortRT10.3，在转化yolov8模型时出现报错
[03/17/2025-10:49:58] [W] [TRT] UNSUPPORTED_STATE: Skipping tactic 0 due to insufficient memory on requested size of 352976 detected for tactic 0x0000000000000000.
[03/17/2025-10:49:58] [W] [TRT] UNSUPPORTED_STATE: Skipping tactic 0 due to insufficient memory on requested size of 180840 detected for tactic 0x0000000000000000.
[03/17/2025-10:49:58] [W] [TRT] UNSUPPORTED_STATE: Skipping tactic 0 due to insufficient memory on requested size of 180840 detected for tactic 0x0000000000000000.
[03/17/2025-10:49:58] [E] Error[4]: IBuilder::buildSerializedNetwork: Error Code 4: Internal Error (Could not find any implementation for node {ForeignNode[/0/model.22/Split_1_27.../1/Concat]} due to insufficient workspace. See verbose log for requested sizes.)
[03/17/2025-10:49:58] [E] Engine could not be created from network
[03/17/2025-10:49:58] [E] Building engine failed
[03/17/2025-10:49:58] [E] Failed to create engine from model or file.
[03/17/2025-10:49:58] [E] Engine set up failed
使用jetson orin nx super，此前在jetpack6.0上运行良好，更新为jetpack6.2时运行自己的deepstream出现无法加载sgie的engine模型。当我尝试在nx super上重新进行pt-onnx-engine的转换过程中出现上述报错。
请问该如何解决？
Environment
TensorRT Version: 10.3
GPU Type: jetson orin nx
Nvidia Driver Version:
CUDA Version: 12.6
CUDNN Version: 9.3
Operating System + Version:
Python Version (if applicable): 3.10
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):